Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3301 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.4082. Min Act: -0.0000

Data Index: 102558 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3303. Min Act: -0.0000

Data Index: 938561 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3819. Min Act: -0.0000

Data Index: 757600 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3427. Min Act: -0.0000

Data Index: 112342 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3337. Min Act: -0.0000

Data Index: 949215 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3112. Min Act: -0.0000

Data Index: 509551 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2891. Min Act: -0.0000

Data Index: 244578 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1199756 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1326265 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2932. Min Act: -0.0000

Data Index: 589052 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1143157 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2988. Min Act: -0.0000

Data Index: 253201 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2976. Min Act: -0.0000

Data Index: 674566 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2601. Min Act: -0.0000

Data Index: 302628 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2515. Min Act: -0.0000

Data Index: 1091914 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2521. Min Act: -0.0000

Data Index: 784703 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2784. Min Act: -0.0000

Data Index: 661151 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2565. Min Act: -0.0000

Data Index: 822594 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1080008 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1138423 (C4 (Web Text))

Max Activating Token Index: 506